A generalizable deep voxel-guided morphometry algorithm for the detection of subtle lesion dynamics in multiple sclerosis

• Verfasst von: Raj, Anish [VerfasserIn]
• Verfasst von: Gass, Achim [VerfasserIn]
• Verfasst von: Eisele, Philipp [VerfasserIn]
• Verfasst von: Dabringhaus, Andreas [VerfasserIn]
• Verfasst von: Kraemer, Matthias [VerfasserIn]
• Verfasst von: Zöllner, Frank G. [VerfasserIn]
• Titel: A generalizable deep voxel-guided morphometry algorithm for the detection of subtle lesion dynamics in multiple sclerosis
• Verf.angabe: Anish Raj, Achim Gass, Philipp Eisele, Andreas Dabringhaus, Matthias Kraemer and Frank G. Zöllner
• E-Jahr: 2024
• Jahr: 25 January 2024
• Umfang: 11 S.
• Fussnoten: Gesehen am 26.03.2024
• Titel Quelle: Enthalten in: Frontiers in neuroscience
• Ort Quelle: Lausanne : Frontiers Research Foundation, 2007
• Jahr Quelle: 2024
• Band/Heft Quelle: 18(2024) vom: Jan., Artikel-ID 1326108, Seite 1-11
• ISSN Quelle: 1662-453X
• DOI: doi:10.3389/fnins.2024.1326108
• Datenträger: Online-Ressource
• Sprache: eng
• Sach-SW: attention mechanism
• Sach-SW: brain MRI
• Sach-SW: deep learning
• Sach-SW: Generalizability
• Sach-SW: longitudinal change detection map
• Sach-SW: Multiple Sclerosis
• Sach-SW: voxel guided morphometry
• K10plus-PPN: 1884398553
• K10plus-PPN:
  Universitätsbibliothek
• Lokale URL UB: Zum Volltext

Abstract

<sec><title>Introduction</title><p>Multiple sclerosis (MS) is a chronic neurological disorder characterized by the progressive loss of myelin and axonal structures in the central nervous system. Accurate detection and monitoring of MS-related changes in brain structures are crucial for disease management and treatment evaluation. We propose a deep learning algorithm for creating Voxel-Guided Morphometry (VGM) maps from longitudinal MRI brain volumes for analyzing MS disease activity. Our approach focuses on developing a generalizable model that can effectively be applied to unseen datasets.</p></sec><sec><title>Methods</title><p>Longitudinal MS patient high-resolution 3D T1-weighted follow-up imaging from three different MRI systems were analyzed. We employed a 3D residual U-Net architecture with attention mechanisms. The U-Net serves as the backbone, enabling spatial feature extraction from MRI volumes. Attention mechanisms are integrated to enhance the model's ability to capture relevant information and highlight salient regions. Furthermore, we incorporate image normalization by histogram matching and resampling techniques to improve the networks' ability to generalize to unseen datasets from different MRI systems across imaging centers. This ensures robust performance across diverse data sources.</p></sec><sec><title>Results</title><p>Numerous experiments were conducted using a dataset of 71 longitudinal MRI brain volumes of MS patients. Our approach demonstrated a significant improvement of 4.3% in mean absolute error (MAE) against the state-of-the-art (SOTA) method. Furthermore, the algorithm's generalizability was evaluated on two unseen datasets (<italic>n</italic> = 116) with an average improvement of 4.2% in MAE over the SOTA approach.</p></sec><sec><title>Discussion</title><p>Results confirm that the proposed approach is fast and robust and has the potential for broader clinical applicability.</p></sec>